Unverified50% confidenceFactExact time
The QDRAG framework contains two key steps: query decomposition and reranking-based pruning.
1
Sources
50%
Confidence
Long-term
Relevance
11/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQDRAG proposes two zero-shot query decomposition methods: QD-C (based on contextual knowledge) and QD-R (based on retrieval rewards).73% similarUnverifiedQdrant natively supports combining payload filtering in vector retrieval, builds indexes on payload fields, and traverses while incorporating filter conditions during HNSW graph search.67% similarUnverifiedQwen establishes dedicated lookup tables for phrase-level token combinations at the input stage through N-gram embeddings, concentrated in a large lookup layer at the front end of the model.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1165023API
curl https://kongchang.com/api/v1/knowledge/claims/1165023MCP
get_claim(id=1165023)